English

Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space

Cryptography and Security 2024-09-24 v1 Artificial Intelligence Machine Learning

Abstract

This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architecture. By developing a confidence metric derived from latent space representations, we aim to improve the reliability of IDS predictions against cyberattacks. Applied to the NSL-KDD dataset, our approach focuses on binary classification tasks to effectively distinguish between normal and malicious network activities. The methodology demonstrates a significant enhancement in anomaly detection, evidenced by a notable correlation of 0.45 between the reconstruction error and the proposed metric. Our findings highlight the potential of employing VAEs for more accurate and trustworthy anomaly detection in network security.

Keywords

Cite

@article{arxiv.2409.13774,
  title  = {Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space},
  author = {Ioannis Pitsiorlas and George Arvanitakis and Marios Kountouris},
  journal= {arXiv preprint arXiv:2409.13774},
  year   = {2024}
}

Comments

7 pages

R2 v1 2026-06-28T18:51:48.992Z